© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89258
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    clinical study-related terminology and findings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on precise decimal or fractional numeric values (floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FindBy
    -0.07
     Produto
    -0.06
    208
    -0.06
     Gate
    -0.06
    arez
    -0.06
     valley
    -0.06
    nov
    -0.06
     Yani
    -0.06
    arakter
    -0.06
    Notification
    -0.06
    POSITIVE LOGITS
    .completed
    0.07
     mọi
    0.07
    .Sql
    0.07
     vých
    0.07
     yaygın
    0.07
     VIA
    0.06
    _todo
    0.06
    nell
    0.06
    {-#
    0.06
     autre
    0.06
    Activations Density 0.062%

    No Known Activations